© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2754
    Prev
    Next
    INDEX
    Explanations

    hydration and electrolytes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æijĩ
    -0.09
    æı½
    -0.09
    å¯ħ
    -0.08
     Glover
    -0.08
    ä¸įåıĹ
    -0.08
    æ²ī
    -0.08
    å·¨
    -0.08
    åѵåĮĸ
    -0.08
    jure
    -0.08
    ODO
    -0.08
    POSITIVE LOGITS
     electroly
    0.11
    补水
    0.10
     dehydration
    0.10
    æ´¥
    0.10
    æ±Ĺ
    0.09
    liqu
    0.09
    å¸ĤåľºåĮĸ
    0.09
    BG
    0.09
    _iterations
    0.09
    çĶµè§£
    0.08
    Activations Density 0.092%

    No Known Activations